test: add pytest coverage for core graph executor success and failure paths

core/examples/manual_agent.py

@@ -13,11 +13,12 @@
 """
 
 import asyncio
-import logging
-from framework.graph import Goal, NodeSpec, EdgeSpec, GraphSpec, EdgeCondition
+
+from framework.graph import EdgeCondition, EdgeSpec, Goal, GraphSpec, NodeSpec
 from framework.graph.executor import GraphExecutor
 from framework.runtime.core import Runtime
 
+
 # 1. Define Node Logic (Pure Python Functions)
 def greet(name: str) -> str:
     """Generate a simple greeting."""
@@ -38,7 +39,7 @@ async def main():
         description="Generate a friendly uppercase greeting",
         success_criteria=[
             {
-                "id": "greeting_generated", 
+                "id": "greeting_generated",
                 "description": "Greeting produced",
                 "metric": "custom",
                 "target": "any"
@@ -63,7 +64,7 @@ async def main():
         name="Uppercaser",
         description="Converts greeting to uppercase",
         node_type="function",
-        function="uppercase", 
+        function="uppercase",
         input_keys=["greeting"],
         output_keys=["final_greeting"]
     )
@@ -100,8 +101,8 @@ async def main():
     executor.register_function("uppercaser", uppercase)
 
     # 8. Execute Agent
-    print(f"▶ Executing agent with input: name='Alice'...")
-    
+    print("▶ Executing agent with input: name='Alice'...")
+
     result = await executor.execute(
         graph=graph,
         goal=goal,

core/framework/__init__.py

@@ -22,22 +22,22 @@
 See `framework.testing` for details.
 """
 
-from framework.schemas.decision import Decision, Option, Outcome, DecisionEvaluation
-from framework.schemas.run import Run, RunSummary, Problem
-from framework.runtime.core import Runtime
 from framework.builder.query import BuilderQuery
-from framework.llm import LLMProvider, AnthropicProvider
-from framework.runner import AgentRunner, AgentOrchestrator
+from framework.llm import AnthropicProvider, LLMProvider
+from framework.runner import AgentOrchestrator, AgentRunner
+from framework.runtime.core import Runtime
+from framework.schemas.decision import Decision, DecisionEvaluation, Option, Outcome
+from framework.schemas.run import Problem, Run, RunSummary
 
 # Testing framework
 from framework.testing import (
+    ApprovalStatus,
+    DebugTool,
+    ErrorCategory,
     Test,
     TestResult,
-    TestSuiteResult,
     TestStorage,
-    ApprovalStatus,
-    ErrorCategory,
-    DebugTool,
+    TestSuiteResult,
 )
 
 __all__ = [

core/framework/builder/__init__.py

@@ -2,12 +2,12 @@
 
 from framework.builder.query import BuilderQuery
 from framework.builder.workflow import (
-    GraphBuilder,
-    BuildSession,
     BuildPhase,
-    ValidationResult,
+    BuildSession,
+    GraphBuilder,
     TestCase,
     TestResult,
+    ValidationResult,
 )
 
 __all__ = [

core/framework/builder/query.py

@@ -8,12 +8,12 @@
 4. What should we change? (suggestions)
 """
 
-from typing import Any
 from collections import defaultdict
 from pathlib import Path
+from typing import Any
 
 from framework.schemas.decision import Decision
-from framework.schemas.run import Run, RunSummary, RunStatus
+from framework.schemas.run import Run, RunStatus, RunSummary
 from framework.storage.backend import FileStorage
 
 
@@ -476,7 +476,7 @@ def _find_differences(self, run1: Run, run2: Run) -> list[str]:
             )
 
         # Find first divergence point
-        for i, (d1, d2) in enumerate(zip(run1.decisions, run2.decisions)):
+        for i, (d1, d2) in enumerate(zip(run1.decisions, run2.decisions, strict=False)):
             if d1.chosen_option_id != d2.chosen_option_id:
                 differences.append(
                     f"Diverged at decision {i}: chose '{d1.chosen_option_id}' vs '{d2.chosen_option_id}'"

core/framework/builder/workflow.py

@@ -13,16 +13,17 @@
 You cannot skip steps or bypass validation.
 """
 
+from collections.abc import Callable
+from datetime import datetime
 from enum import Enum
 from pathlib import Path
-from datetime import datetime
-from typing import Any, Callable
+from typing import Any
 
 from pydantic import BaseModel, Field
 
+from framework.graph.edge import EdgeCondition, EdgeSpec, GraphSpec
 from framework.graph.goal import Goal
 from framework.graph.node import NodeSpec
-from framework.graph.edge import EdgeSpec, EdgeCondition, GraphSpec
 
 
 class BuildPhase(str, Enum):
@@ -630,69 +631,69 @@ def _generate_code(self, graph: GraphSpec) -> str:
         """Generate Python code for the graph."""
         lines = [
             '"""',
-            f'Generated agent: {self.session.name}',
-            f'Generated at: {datetime.now().isoformat()}',
+            f"Generated agent: {self.session.name}",
+            f"Generated at: {datetime.now().isoformat()}",
             '"""',
-            '',
-            'from framework.graph import (',
-            '    Goal, SuccessCriterion, Constraint,',
-            '    NodeSpec, EdgeSpec, EdgeCondition,',
-            ')',
-            'from framework.graph.edge import GraphSpec',
-            'from framework.graph.goal import GoalStatus',
-            '',
-            '',
-            '# Goal',
+            "",
+            "from framework.graph import (",
+            "    Goal, SuccessCriterion, Constraint,",
+            "    NodeSpec, EdgeSpec, EdgeCondition,",
+            ")",
+            "from framework.graph.edge import GraphSpec",
+            "from framework.graph.goal import GoalStatus",
+            "",
+            "",
+            "# Goal",
         ]
 
         if self.session.goal:
             goal_json = self.session.goal.model_dump_json(indent=4)
-            lines.append('GOAL = Goal.model_validate_json(\'\'\'')
+            lines.append("GOAL = Goal.model_validate_json('''")
             lines.append(goal_json)
             lines.append("''')")
         else:
-            lines.append('GOAL = None')
+            lines.append("GOAL = None")
 
         lines.extend([
-            '',
-            '',
-            '# Nodes',
-            'NODES = [',
+            "",
+            "",
+            "# Nodes",
+            "NODES = [",
         ])
 
         for node in self.session.nodes:
             node_json = node.model_dump_json(indent=4)
-            lines.append('    NodeSpec.model_validate_json(\'\'\'')
+            lines.append("    NodeSpec.model_validate_json('''")
             lines.append(node_json)
             lines.append("    '''),")
 
         lines.extend([
-            ']',
-            '',
-            '',
-            '# Edges',
-            'EDGES = [',
+            "]",
+            "",
+            "",
+            "# Edges",
+            "EDGES = [",
         ])
 
         for edge in self.session.edges:
             edge_json = edge.model_dump_json(indent=4)
-            lines.append('    EdgeSpec.model_validate_json(\'\'\'')
+            lines.append("    EdgeSpec.model_validate_json('''")
             lines.append(edge_json)
             lines.append("    '''),")
 
         lines.extend([
-            ']',
-            '',
-            '',
-            '# Graph',
+            "]",
+            "",
+            "",
+            "# Graph",
         ])
 
         graph_json = graph.model_dump_json(indent=4)
-        lines.append('GRAPH = GraphSpec.model_validate_json(\'\'\'')
+        lines.append("GRAPH = GraphSpec.model_validate_json('''")
         lines.append(graph_json)
         lines.append("''')")
 
-        return '\n'.join(lines)
+        return "\n".join(lines)
 
     # =========================================================================
     # SESSION MANAGEMENT

core/framework/graph/__init__.py

@@ -1,32 +1,32 @@
 """Graph structures: Goals, Nodes, Edges, and Flexible Execution."""
 
-from framework.graph.goal import Goal, SuccessCriterion, Constraint, GoalStatus
-from framework.graph.node import NodeSpec, NodeContext, NodeResult, NodeProtocol
-from framework.graph.edge import EdgeSpec, EdgeCondition, GraphSpec
+from framework.graph.code_sandbox import CodeSandbox, safe_eval, safe_exec
+from framework.graph.edge import EdgeCondition, EdgeSpec, GraphSpec
 from framework.graph.executor import GraphExecutor
+from framework.graph.flexible_executor import ExecutorConfig, FlexibleGraphExecutor
+from framework.graph.goal import Constraint, Goal, GoalStatus, SuccessCriterion
+from framework.graph.judge import HybridJudge, create_default_judge
+from framework.graph.node import NodeContext, NodeProtocol, NodeResult, NodeSpec
 
 # Flexible execution (Worker-Judge pattern)
 from framework.graph.plan import (
-    Plan,
-    PlanStep,
     ActionSpec,
     ActionType,
-    StepStatus,
-    Judgment,
-    JudgmentAction,
-    EvaluationRule,
-    PlanExecutionResult,
-    ExecutionStatus,
-    load_export,
     # HITL (Human-in-the-loop)
     ApprovalDecision,
     ApprovalRequest,
     ApprovalResult,
+    EvaluationRule,
+    ExecutionStatus,
+    Judgment,
+    JudgmentAction,
+    Plan,
+    PlanExecutionResult,
+    PlanStep,
+    StepStatus,
+    load_export,
 )
-from framework.graph.judge import HybridJudge, create_default_judge
-from framework.graph.worker_node import WorkerNode, StepExecutionResult
-from framework.graph.flexible_executor import FlexibleGraphExecutor, ExecutorConfig
-from framework.graph.code_sandbox import CodeSandbox, safe_exec, safe_eval
+from framework.graph.worker_node import StepExecutionResult, WorkerNode
 
 __all__ = [
     # Goal

core/framework/graph/code_sandbox.py

@@ -13,11 +13,11 @@
 """
 
 import ast
-import sys
 import signal
-from typing import Any
-from dataclasses import dataclass, field
+import sys
 from contextlib import contextmanager
+from dataclasses import dataclass, field
+from typing import Any
 
 # Safe builtins whitelist
 SAFE_BUILTINS = {
@@ -216,7 +216,7 @@ def handler(signum, frame):
             raise TimeoutError(f"Code execution timed out after {seconds} seconds")
 
         # Only works on Unix-like systems
-        if hasattr(signal, 'SIGALRM'):
+        if hasattr(signal, "SIGALRM"):
             old_handler = signal.signal(signal.SIGALRM, handler)
             signal.alarm(seconds)
             try:

core/framework/graph/edge.py

@@ -22,8 +22,8 @@
 given the current goal, context, and execution state.
 """
 
-from typing import Any
 from enum import Enum
+from typing import Any
 
 from pydantic import BaseModel, Field
 
@@ -238,7 +238,7 @@ def _llm_decide(
 
             # Parse response
             import re
-            json_match = re.search(r'\{[^{}]*\}', response.content, re.DOTALL)
+            json_match = re.search(r"\{[^{}]*\}", response.content, re.DOTALL)
             if json_match:
                 data = json.loads(json_match.group())
                 proceed = data.get("proceed", False)

core/framework/graph/executor.py

@@ -10,25 +10,26 @@
 """
 
 import logging
-from typing import Any, Callable
+from collections.abc import Callable
 from dataclasses import dataclass, field
+from typing import Any
 
-from framework.runtime.core import Runtime
+from framework.graph.edge import GraphSpec
 from framework.graph.goal import Goal
 from framework.graph.node import (
-    NodeSpec,
+    FunctionNode,
+    LLMNode,
     NodeContext,
-    NodeResult,
     NodeProtocol,
-    SharedMemory,
-    LLMNode,
+    NodeResult,
+    NodeSpec,
     RouterNode,
-    FunctionNode,
+    SharedMemory,
 )
-from framework.graph.edge import GraphSpec
+from framework.graph.output_cleaner import CleansingConfig, OutputCleaner
 from framework.graph.validator import OutputValidator
-from framework.graph.output_cleaner import OutputCleaner, CleansingConfig
 from framework.llm.provider import LLMProvider, Tool
+from framework.runtime.core import Runtime
 
 
 @dataclass